Skip to content

Instantly share code, notes, and snippets.

@dipanjanS

dipanjanS/tfserve_vision9.py

Last active March 1, 2020 21:36
Show Gist options
  • Save dipanjanS/51432e98a4e17bbf38e056e7aa8c9634 to your computer and use it in GitHub Desktop.
Save dipanjanS/51432e98a4e17bbf38e056e7aa8c9634 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
tfserve_vision9.py
EPOCHS = 10
train_images_3ch_scaled = train_images_3ch / 255.
model2.fit(train_images_3ch_scaled, train_labels, validation_split=0.1,
epochs=EPOCHS)
# Output
Train on 54000 samples, validate on 6000 samples
Epoch 1/10
54000/54000 [====] - 100s 2ms/sample - loss: 0.5434 - acc: 0.8299 - val_loss: 0.3318 - val_acc: 0.9043
Epoch 2/10
54000/54000 [====] - 92s 2ms/sample - loss: 0.3186 - acc: 0.9024 - val_loss: 5.9477 - val_acc: 0.8462
...
...
Epoch 9/10
54000/54000 [====] - 92s 2ms/sample - loss: 0.1783 - acc: 0.9486 - val_loss: 0.3744 - val_acc: 0.9252
Epoch 10/10
54000/54000 [====] - 92s 2ms/sample - loss: 0.1645 - acc: 0.9524 - val_loss: 0.3773 - val_acc: 0.9288
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment